相关论文: Strategic Sample Selection for Improved Clean-Labe…

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…

Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…

The goal of hate speech detection is to filter negative online content aiming at certain groups of people. Due to the easy accessibility of social media platforms it is crucial to protect everyone which requires building hate speech…

Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor…

Machine learning has been proven to be susceptible to carefully crafted samples, known as adversarial examples. The generation of these adversarial examples helps to make the models more robust and gives us an insight into the underlying…

Deep neural networks are vulnerable to adversarial attacks. Among different attack settings, the most challenging yet the most practical one is the hard-label setting where the attacker only has access to the hard-label output (prediction…

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks is under-explored. A handful of existing works focus on dirty-label attacks with wrongly-labeled poisoned…

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to…

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a significant increase in the harmfulness of LLM outputs. Building on…

Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative…

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison…

Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to…

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…

Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical…

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

With the rapid development of Deep Neural Networks (DNNs), they have been applied in numerous fields. However, research indicates that DNNs are susceptible to adversarial examples, and this is equally true in the multi-label domain. To…

Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on…